EP3089650B1 - Method and apparatus for colposcopic image analysis with improved reliability - Google Patents

Method and apparatus for colposcopic image analysis with improved reliability Download PDF

Info

Publication number
EP3089650B1
EP3089650B1 EP14821135.2A EP14821135A EP3089650B1 EP 3089650 B1 EP3089650 B1 EP 3089650B1 EP 14821135 A EP14821135 A EP 14821135A EP 3089650 B1 EP3089650 B1 EP 3089650B1
Authority
EP
European Patent Office
Prior art keywords
image
aceto
iodine
region
acetic acid
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP14821135.2A
Other languages
German (de)
English (en)
French (fr)
Other versions
EP3089650A1 (en
Inventor
Subhendu Seth
Pallavi Vajinepalli
Payal Keswarpu
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Koninklijke Philips NV
Original Assignee
Koninklijke Philips NV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Koninklijke Philips NV filed Critical Koninklijke Philips NV
Priority to EP14821135.2A priority Critical patent/EP3089650B1/en
Publication of EP3089650A1 publication Critical patent/EP3089650A1/en
Application granted granted Critical
Publication of EP3089650B1 publication Critical patent/EP3089650B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/303—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor for the vagina, i.e. vaginoscopes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/43—Detecting, measuring or recording for evaluating the reproductive systems
    • A61B5/4306—Detecting, measuring or recording for evaluating the reproductive systems for evaluating the female reproductive systems, e.g. gynaecological evaluations
    • A61B5/4318—Evaluation of the lower reproductive system
    • A61B5/4331—Evaluation of the lower reproductive system of the cervix
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
    • A61M5/007—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests for contrast media
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/174—Segmentation; Edge detection involving the use of two or more images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2576/00—Medical imaging apparatus involving image processing or analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing

Definitions

  • the invention relates to the field of apparatuses and methods for semi-automated or automated aceto-whiteness region detection, representation and quantification for any automated cervical image analysis systems.
  • metaplasia When cells are faced with physiological or pathological stresses, they respond by adapting in any of several ways, one of which is metaplasia. It is a benign (i.e. non-cancerous) change that occurs as a response to change of milieu (physiological metaplasia) or chronic physical or chemical irritation (pathological metaplasia).
  • pathological irritation is cigarette smoke that causes the mucus-secreting ciliated pseudostratified columnar respiratory epithelial cells that line the airways to be replaced by stratified squamous epithelium, or a stone in the bile duct that causes the replacement of the secretory columnar epithelium with stratified squamous epithelium (Squamous metaplasia).
  • metaplasia refers to the change or replacement of one type of epithelium by another. More specifically, metaplasia is an adaptation that replaces one type of epithelium with another that is more likely to be able to withstand the stresses it is faced with. It is also accompanied by a loss of endothelial function, and in some instances considered undesirable. This undesirability is underscored by the propensity for metaplastic regions to eventually turn cancerous if the irritant is not eliminated.
  • metaplasia The medical significance of metaplasia is that in some sites where pathological irritation is present cells may progress from metaplasia, to develop dysplasia, and then malignant neoplasia (cancer). Thus, at sites where abnormal metaplasia is detected, efforts are made to remove the causative irritant, thereby decreasing the risk of progression to malignancy.
  • a transformation zone is an area in the uterine cervix, where columnar epithelium is replaced by squamous epithelium. This is the region where the cancer occurs in the uterine cervix.
  • a 3-5% acetic acid solution is applied to the cervix. Acetic acid causes cellular dehydration and reversible coagulation of intracellular proteins, thus reducing the transparency of the epithelium. This results in temporary whiteness of the epithelium, i.e., aceto-white epithelium.
  • Lugol's iodine also known as Lugol's solution is a solution of elemental iodine and potassium iodide in water, named after the French physician J.G.A. Lugol. Lugol's iodine solution is often used as an antiseptic and disinfectant, for emergency disinfection of drinking water, and as a reagent for starch detection in routine laboratory and medical tests. These uses are possible since the solution is a source of effectively free elemental iodine, which is readily generated from the equilibration between elemental iodine molecules and triiodide ions in the solution.
  • Aceto-whiteness detection, representation and quantification are important features of any automated cervical image analysis systems, like the systems disclosed in document WO 2012/123881 and in the article PALLAVI V ET AL: "Automated analysis of cervix images to grade the severity of cancer",ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY,EMBC, 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE, IEEE, 30 August 2011 (2011-08-30), pages 3439-3442 .
  • PALLAVI V ET AL "Automated analysis of cervix images to grade the severity of cancer”
  • ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY,EMBC 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE, IEEE, 30 August 2011 (2011-08-30)
  • PALLAVI V ET AL "Automated analysis of cervix images to grade the severity of cancer”
  • ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY,EMBC 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE, IEEE
  • false alarms for aceto-white regions in automated image analysis systems can be reduced or isolated by using multi-stained image registration between acetic acid and Lugol's iodine image.
  • a transformation zone is identified in an acetic acid image by registering with an iodine counterpart image of the acetic acid image. Then, a region with more than a predetermined minimum change in whiteness is identified within the transformation zone and the identified region is registered with the iodine counterpart image. Based on the registration of the identified region with the iodine counterpart image, it is decided on a type of iodine uptake of the identified region so as to determine if the identified region comprises a premalignant lesion.
  • transformation zones registered in pre acetic acid and post acetic acid images may be used, e.g. by the zone identifier of claim 1, to identify the region with more than a predetermined minimum change in whiteness due to application of acetic acid. This measure helps in propagating anatomical segmentation of different anatomical regions across different stains.
  • color values of an initial color space (e.g. RGB color space) of the transformation zone in the post acetic acid images may be converted, e.g. by the aceto-white identifier of claim 1, to a color space with a color component (e.g., the L component of the Lab color space) that substantially matches human perception of lightness or whiteness. This ensures that proper discrimination in accordance with human perception can be achieved.
  • an initial color space e.g. RGB color space
  • a color component e.g., the L component of the Lab color space
  • pixels in the identified transformation zone may be clustered, e.g. by the aceto-white identifier of claim 1, based on their opacity change and pixels with an opacity change below a predetermined threshold may be removed. Thereby, a straight forward discrimination among dominant and minor opacity changes can be achieved.
  • clustering based multilevel histogram thresholding may be applied inside the identified transformation zone, e.g. by the aceto-white identifier of claim 1. This measure helps in finding the desired result iteratively
  • information gain based aceto-white region selection my be applied, e.g., by the aceto-white identifier of claim 1.
  • a suitable termination criterion for the above histogram thresholding can be obtained to isolate varied homogeneous regions.
  • a change of intensity of a foreground to background ratio of a post acetic acid image may be compared, e.g. by the aceto-white identifier of claim 1, with that of a pre acetic acid counterpart image.
  • aceto-white regions may readily be identified.
  • a histogram of red channel values of the iodine counterpart image may be generated, peaks of the histogram may be identified, and the type of iodine uptake may be decided based on a threshold at a second peak of the histogram, e.g. by the region separator of claim 1.
  • iodine uptake can be identified and categorized.
  • the above apparatus may be implemented based on discrete hardware circuitry with discrete hardware components, an integrated chip, or an arrangement of chip modules, or based on a signal processing device or chip controlled by a software routine or program stored in a memory, written on a computer readable medium, or downloaded from a network, such as the Internet.
  • Embodiments of the present invention are now described based on an automated colposcopic image analysis system.
  • Colposcopic practice includes the examination of features of the cervical epithelium after application of saline, 3-5% dilute acetic acid, and Lugol's iodine solution in successive steps.
  • the study of the vascular pattern of the cervix may prove difficult after application of acetic acid and iodine solutions.
  • physiological saline before acetic acid and iodine application is useful in studying the subepithelial vascular architecture in great detail.
  • the 3-5% acetic acid is usually applied with a cotton applicator (e.g. cotton balls held by sponge forceps, or large rectal or small swabs) or with a small sprayer. It helps in coagulating and clearing the mucus.
  • Acetic acid is thought to cause swelling of the epithelial tissue, columnar and any abnormal squamous epithelial areas in particular. It causes a reversible coagulation or precipitation of the nuclear proteins and cytokeratins.
  • the effect of acetic acid depends upon the amount of nuclear proteins and cytokeratins present in the epithelium.
  • the principle behind the iodine test is that original and newly formed mature squamous metaplastic epithelium is glycogenated, whereas CIN and invasive cancer contain little or no glycogen.
  • Columnar epithelium does not contain glycogen.
  • Immature squamous metaplastic epithelium usually lacks glycogen or, occasionally, may be partially glycogenated.
  • Iodine is glycophilic and hence the application of iodine solution results in uptake of iodine in glycogen-containing epithelium. Therefore, the normal glycogen-containing squamous epithelium stains mahogany brown or black after application of iodine.
  • Fig. 1 shows a block based representation of aceto-white characteristics. If aceto-whiteness appears fast and lasts long (e.g. for more than 2 min), then a high grade lesion (HGL) can be assumed. Otherwise, if aceto-whiteness appears slowly and disappears quickly (e.g. after less than 2 min), application of Lugol's iodine provides different results of stain depending on the conditions of the epithelium. If no stain (NST) is observed, than high grade lesion (HGL) or low grade lesion (LGL) or immature squamous metaplasia (ISM) can be assumed. If stain (ST) is observed, than mature squamous metaplasia (MSM) can be assumed. Finally, if partial stain (PST) is observed, than inflammation (I) or immature squamous metaplasia (ISM) can be assumed.
  • NST high grade lesion
  • LGL low grade lesion
  • ISM immature
  • the following embodiments are based on the above aceto-white characteristics by applying an analysis where the transformation zone (TZ) is identified in acetic acid images by registering with its Lugol's iodine counterpart. This process is eminent as this will restrict the remaining part of the proposed automated image analysis to the TZ region which is the most probable area for malignant activities. Then, an aceto-white probable region is identified in the TZ, i.e., a region of the TZ, which shows significant changes in whiteness. Identified aceto-white regions are registered (or aligned) in the acetic acid image with a corresponding Lugol's iodine image. Based on the registered images, iodine uptake and FP reduction are assessed and characterized.
  • TZ transformation zone
  • Demarcation of the TZ by registering both the acetic-acid and Lugol's iodine images is a challenging task, as both of them exhibit different colours and textural appearances.
  • procedures for efficient demarcation of the aceto-white region and cross-checking the information from its Lugol's iodine counterpart are described based on first to third embodiments.
  • Fig. 2 shows a schematic flow diagram of an automated image analysis procedure according to a first embodiment.
  • a post or pre acetic acid image (where the inner most boarder of the TZ i.e. a new SCJ (Sqamo-columnar Junction) is prominent) is registered with Lugol's iodine image (where outer most border of TZ i.e. an old SCJ is prominent) of the same patient at the same level of magnification using e.g. phase congruency and consistent elastic registration.
  • Multi-stain images obtained by applying saline, acetic acid and Lugol's iodine having similar magnification levels are registered, which helps in propagating the anatomical segmentation of different anatomical regions across the stains.
  • the TZ i.e. the region between new SCJ and old SCJ
  • the TZ can be identified by registering at least one Lugol's iodine image and one post acetic acid image (i.e. image after application of acetic acid) or at least one Lugol's iodine image and post saline image (i.e. image after application of saline).
  • the new SCJ identified in post acetic acid or post saline image is mapped to Lugol's Iodine image.
  • the old SCJ is identified in Lugol's iodine image.
  • step S210 an aceto-white probable region is identified in the TZ.
  • This can be achieved by using the TZs registered in pre acetic acid (image before application of acetic acid) and post acetic acid images, and identifying those regions that show significant change in whiteness due to the application of acetic acid.
  • the post acetic acid images pixels in the transformation zone which show dominant opacity changes are identified and they are compared with their corresponding pixels in pre acetic acid image.
  • Figs. 5A and 5B show exemplary results of detected and marked aceto-white regions 10.
  • aceto-white regions are registered in step S220 for further steps using phase congruency and multi stain registration with a corresponding Lugol's iodine image.
  • Both images i.e. acetic and Lugol's iodine image
  • This is a special kind of bi-directional registration which consists of combination of elastic image registration based on B-Splines models and consistent image registration. Further details can be gathered from Arganda-Carreras, I., Sorzano, C. O.
  • step S230 the Lugol's iodine image is thresholded to separate the regions with mustard yellow and dark brown colour.
  • the main aim of this step is to identify the iodine uptake of the regions in Lugol's iodine image. Thresholding can be applied by considering the red channel of the Lugol's iodine image, plotting a histogram for red channel values, smoothing the histogram, identifying its peaks and valleys, and setting a threshold at the second peak to segment mustard yellow regions.
  • step S240 it is determined whether a predetermined percentage (e.g. 80%) of the pixels in aceto-white region correspond to mustard yellow color. If so, then the procedure branches off to step S260 and the iodine uptake is categorized as "iodine negative", else the procedure continues with step S250 and the iodine uptake it is categorized as "iodine positive”. If the aceto-white region is identified to be “iodine positive” then it is metaplasia else a premalignant lesion.
  • a predetermined percentage e.g. 80%
  • Figs. 6A and 6B show exemplary results of identified iodine uptake 20 by registering aceto-white regions in a Lugol's iodine image.
  • Fig. 3 shows a schematic flow diagram of a clustering based aceto-white region segmentation procedure according to the second embodiment.
  • step S310 RGB (red, green and blue color) values of the transformation zone in post acetic acid images are converted to the Lab colour space.
  • the Lab color space is a color-opponent space with dimension "L” for lightness and "a" and "b” for the color-opponent dimensions, based on nonlinearly compressed XYZ color space coordinates of the International Commission on Illumination (CIE).
  • CIE International Commission on Illumination
  • the "L” component closely matches human perception of lightness/whiteness.
  • step S320 pixels are clustered in the transformation zone to two levels of whitish regions, i.e., dominant opacity change and minor opacity change using K-means clustering used to match opaque white and translucent white.
  • K-means clustering is a method of vector quantization and aims at partitioning n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. Thereafter, in step S330, pixels with minor opacity change are removed and finally, in step S340, the corresponding pixels of the dominant opacity change in the pre-acetic acid image are identified.
  • Fig. 4 shows a schematic flow diagram of an information gain based aceto-white region segmentation procedure as an alternative approach for aceto-whiteness detection according to a third embodiment.
  • step S410 clustering based multilevel histogram thresholding is applied, where a multilevel thresholding process segments grey scale image (inside the TZ region) into several different similar (based on grey scale) regions.
  • the maximum and minimum thresholds are derived from the dataset. Further details are described for example in Seth, S., Naik, S., Jayavanth, S., and Keswarpu, P., "Nucleus Segmentation in Pap-smear Images", ICBME, 2011 . This will help in finding the desired result iteratively. However farther steps is needed to terminate the region grow (with the change of threshold) to achieve the aceto-white regions.
  • step S420 information gain based aceto-white region segmentation is applied.
  • This information gain based homogeneous region identification serves to isolate aceto-white probable regions.
  • Step S420 is able to bring the suitable termination criteria for step S410 to isolate varied homogeneous regions. The procedure jumps back to step S410 until this termination criteria is met.
  • a further step S430 is performed. Namely, feature based aceto-white region selection. Due to the presence of aceto-white appearance, the foreground to background ratio of post acetic image shows a significant increment in intensity when compared to its pre-acetic counterpart. This feature can be leveraged to isolate aceto-white region from its rest.
  • a method and an apparatus for cervical image analysis have been described, wherein a transformation zone is identified in an acetic acid image by registering with its Lugol's iodine counterpart. Then, regions in the transformation zone which show significant changes in whiteness are identified as aceto-white regions and registered with the corresponding Lugol's iodine image, and it is determined if the identified regions in the Lugol's iodine image are iodine negative or positive. Based thereon, the aceto-white region can be categorized as one of metaplasia, inflammation or premalignant lesion region.
  • a single unit or device may fulfill the functions of several items recited in the claims.
  • the mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
  • the described operations like those indicated in Figs. 2 to 4 are implemented as program code means of a computer program and/or as dedicated hardware.
  • the computer program may be stored and/or distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Pathology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Biophysics (AREA)
  • Reproductive Health (AREA)
  • Gynecology & Obstetrics (AREA)
  • Molecular Biology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Vascular Medicine (AREA)
  • Anesthesiology (AREA)
  • Hematology (AREA)
  • Optics & Photonics (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)
  • Endoscopes (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
EP14821135.2A 2013-12-30 2014-12-17 Method and apparatus for colposcopic image analysis with improved reliability Active EP3089650B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP14821135.2A EP3089650B1 (en) 2013-12-30 2014-12-17 Method and apparatus for colposcopic image analysis with improved reliability

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
EP13199747 2013-12-30
EP14821135.2A EP3089650B1 (en) 2013-12-30 2014-12-17 Method and apparatus for colposcopic image analysis with improved reliability
PCT/EP2014/078181 WO2015101496A1 (en) 2013-12-30 2014-12-17 Method and apparatus for cervical image analysis with improved reliability

Publications (2)

Publication Number Publication Date
EP3089650A1 EP3089650A1 (en) 2016-11-09
EP3089650B1 true EP3089650B1 (en) 2021-10-27

Family

ID=49885081

Family Applications (1)

Application Number Title Priority Date Filing Date
EP14821135.2A Active EP3089650B1 (en) 2013-12-30 2014-12-17 Method and apparatus for colposcopic image analysis with improved reliability

Country Status (6)

Country Link
US (1) US10497114B2 (ja)
EP (1) EP3089650B1 (ja)
JP (1) JP6653652B2 (ja)
CN (1) CN105874508B (ja)
RU (1) RU2703507C2 (ja)
WO (1) WO2015101496A1 (ja)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107220975B (zh) 2017-07-31 2018-03-09 合肥工业大学 宫颈图像智能辅助判断***及其处理方法
CN108388841B (zh) * 2018-01-30 2021-04-16 浙江大学 基于多特征深度神经网络的宫颈活检区域识别方法及装置
CN108961222A (zh) * 2018-06-19 2018-12-07 江西大福医疗科技股份有限公司 一种基于***镜图像的***早期筛查识别方法
CN108876786B (zh) * 2018-07-16 2021-10-01 南昌航空大学 一种基于模糊推理的高等级宫颈上皮内瘤变判别方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2240041C1 (ru) * 2003-02-27 2004-11-20 Московский областной научно-исследовательский институт акушерства и гинекологии Способ диагностики воспалительных заболеваний шейки матки
JP4980779B2 (ja) 2007-04-13 2012-07-18 富士フイルム株式会社 撮影装置、方法およびプログラム
WO2009058171A2 (en) * 2007-08-03 2009-05-07 Sti Medical Systems, Llc Computerized image analysis for a acetic acid induced cervical intraepithelial neoplasia
US8483454B2 (en) 2008-10-10 2013-07-09 Sti Medical Systems, Llc Methods for tissue classification in cervical imagery
CN103096786A (zh) * 2010-05-03 2013-05-08 国际科学技术医疗***有限责任公司 宫颈瘤变检测和诊断的图像分析
JP2012142872A (ja) * 2011-01-06 2012-07-26 Fuji Xerox Co Ltd 画像処理装置及び画像処理プログラム
US9107569B2 (en) 2011-03-16 2015-08-18 Koninklijke Philips N.V. Medical instrument for examining the cervix

Also Published As

Publication number Publication date
US10497114B2 (en) 2019-12-03
JP6653652B2 (ja) 2020-02-26
RU2703507C2 (ru) 2019-10-17
WO2015101496A1 (en) 2015-07-09
US20160328845A1 (en) 2016-11-10
EP3089650A1 (en) 2016-11-09
CN105874508B (zh) 2020-06-05
CN105874508A (zh) 2016-08-17
RU2016131017A (ru) 2018-02-07
RU2016131017A3 (ja) 2018-08-07
JP2017507678A (ja) 2017-03-23

Similar Documents

Publication Publication Date Title
Waheed et al. An efficient machine learning approach for the detection of melanoma using dermoscopic images
EP2188779B1 (en) Extraction method of tongue region using graph-based approach and geometric properties
CN108133476B (zh) 一种肺结节自动检测方法及***
Sedivy et al. Fractal analysis: an objective method for identifying atypical nuclei in dysplastic lesions of the cervix uteri
CA2474417A1 (en) Image processing using measures of similarity
CN109815888B (zh) 一种基于新型巴氏染色方法的异常宫颈细胞自动识别方法
Jaafar et al. Detection of exudates in retinal images using a pure splitting technique
EP3089650B1 (en) Method and apparatus for colposcopic image analysis with improved reliability
Bai et al. Automatic segmentation of cervical region in colposcopic images using K-means
CN104299242B (zh) 基于ngc‑acm的荧光造影眼底图像提取方法
JP2007236939A (ja) ***辺縁検出のための方法および装置
CN103325128A (zh) 一种智能识别***镜所采集的图像特征的方法及装置
Patil et al. Image processing based abnormal blood cells detection
Mohan et al. Exudate localization in retinal fundus images using modified speeded up robust features algorithm
Lu et al. Immunohistochemical quantification of expression of a tight junction protein, claudin-7, in human lung cancer samples using digital image analysis method
Manjaramkar et al. Connected component clustering based hemorrhage detection in color fundus images
US20220366561A1 (en) Image acquire devide, cancer determination device, cancer determination method, and computer-readable medium
Pallavi et al. Automated analysis of cervix images to grade the severity of cancer
Sharma et al. A survey on classification of malignant melanoma and benign skin lesion by using machine learning techniques
Guarracino et al. Segmenting dermoscopic images
Siddalingaswamy et al. Automated detection of optic disc and exudates in retinal images
Kavyashree et al. A Survey on the Cervical Cancer Detection using Deep Learning methods
Basha et al. On the Use of Spatial Frequency Technique for Detection of Brain Tumors in Medical Images
Ma et al. Fused 3-stage image segmentation for pleural effusion cell clusters
Sudha Rani et al. Medical Imaging Analysis of Anomalies in Diabetic Nephropathy

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20160801

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAX Request for extension of the european patent (deleted)
RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: KONINKLIJKE PHILIPS N.V.

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Ref document number: 602014080920

Country of ref document: DE

Free format text: PREVIOUS MAIN CLASS: A61B0001303000

Ipc: G06T0007000000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: A61B 5/00 20060101ALI20210430BHEP

Ipc: G06T 7/00 20170101AFI20210430BHEP

INTG Intention to grant announced

Effective date: 20210526

RIN1 Information on inventor provided before grant (corrected)

Inventor name: KESWARPU, PAYAL

Inventor name: VAJINEPALLI, PALLAVI

Inventor name: SETH, SUBHENDU

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: AT

Ref legal event code: REF

Ref document number: 1442502

Country of ref document: AT

Kind code of ref document: T

Effective date: 20211115

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602014080920

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG9D

REG Reference to a national code

Ref country code: NL

Ref legal event code: MP

Effective date: 20211027

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1442502

Country of ref document: AT

Kind code of ref document: T

Effective date: 20211027

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20220127

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20220227

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20220228

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20220127

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20220128

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602014080920

Country of ref document: DE

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

REG Reference to a national code

Ref country code: BE

Ref legal event code: MM

Effective date: 20211231

26N No opposition filed

Effective date: 20220728

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20211217

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20211217

Ref country code: AL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20211227

Ref country code: BE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20211231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20211231

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20211231

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO

Effective date: 20141217

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20231219

Year of fee payment: 10

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20211027

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20231227

Year of fee payment: 10